Cutter/rock interaction modeling

Abstract

A computer-implemented method may include receiving test data representing a cutter/rock interaction for a cutter/rock pair; calibrating an analytical model to represent the cutter/rock interaction mechanism for a cutter/rock pair; applying the calibrated analytical model to expand the test data to form one of a plurality of expanded test datasets; generating a first neural network model, of a plurality of first neural network models, representing cutter/rock interaction between a plurality of cutters of different cutter sizes and a particular rock type, wherein the first neural network is generated using the plurality of expanded test datasets as training input; generating a second neural network model using the plurality of first neural network models as training input, wherein the second neural network model represents non-tested cutter/rock interactions between a plurality of cutters of different cutter sizes and a plurality of rock types.

What is claimed is: 
     
       1. A computer-implemented method comprising:
 receiving test data representing a cutter/rock interaction for a cutter/rock pair; 
 calibrating an analytical model to represent the cutter/rock interaction for the cutter/rock pair; 
 applying the calibrated analytical model to expand the test data to form one of a plurality of expanded test datasets; 
 generating a first neural network model, of a plurality of first neural network models, representing cutter/rock interactions between a plurality of cutters of different cutter sizes and a particular rock type, wherein the first neural network is generated using the plurality of expanded test datasets as training input; and 
 generating a second neural network model using the plurality of first neural network models as training input, wherein the second neural network model represents non-tested cutter/rock interactions between a plurality of cutters of different cutter sizes and a plurality of rock types. 
 
     
     
       2. The method of  claim 1 , further comprising:
 determining cutter force estimates using the second neural network model, wherein the cutter force estimates are determined for the non-tested cutter/rock interactions; and 
 executing a computer-based instruction based on the second neural network model or the cutter force estimates, wherein the computer-based instruction includes at least one selected from the group consisting of:
 executing a computer-based simulation based on the cutter force estimates; 
 adjusting a drilling plan based on results of the computer-based simulation; 
 adjusting a maintenance plan based the results of the computer-based simulation; 
 adjusting operations of a cutter based on the results of the computer-based simulation; 
 modifying a workflow based on the results of the computer-based simulation; 
 providing the calibrated analytical model or data derived from the calibrated analytical model to a simulation system; 
 providing the first neural network model or data derived from the first neural network model to a simulation system; 
 providing the second neural network model or data derived from the second neural network model to a simulation system; 
 setting up automatic synthetic rock file generation workflow; and 
 visually presenting the second neural network model or visually present cutter/rock interaction information. 
 
 
     
     
       3. The method of  claim 1 , further comprising refining the first neural network model or the second neural network model based on experimental data. 
     
     
       4. The method of  claim 1 , wherein the calibrated analytical model is calibrated using model-based inversion. 
     
     
       5. The method of  claim 1 , wherein the calibrated analytical model is a 3D model. 
     
     
       6. The method of  claim 1 , wherein the training the first neural network and the training the second neural network are based on machine learning techniques. 
     
     
       7. The method of  claim 1 , wherein:
 the first neural network is used to obtain cutter rock forces based on:
 cutter size, 
 confinement pressure, 
 back rake angle, 
 side rake angle, and 
 depth; and 
 
 the second neural network model is used to obtain cutter rock forces based on:
 rock type, 
 cutter size, 
 confinement pressure, 
 back rake angle, 
 side rake angle, and 
 depth. 
 
 
     
     
       8. A computing system, comprising:
 one or more processors; and 
 a memory system comprising one or more non-transitory computer-readable media storing instructions that, when executed by at least one of the one or more processors, cause the computing system to perform operations, the operations comprising:
 receiving test data representing a cutter/rock interaction for a cutter/rock pair; 
 calibrating an analytical model to represent the cutter/rock interaction for the cutter/rock pair; 
 applying the calibrated analytical model to expand the test data to form one of a plurality of expanded test datasets; 
 generating a first neural network model, of a plurality of first neural network models, representing cutter/rock interactions between a plurality of cutters of different cutter sizes and a particular rock type, wherein the first neural network is generated using the plurality of expanded test datasets as training input; and 
 generating a second neural network model using the plurality of first neural network models as training input, wherein the second neural network model represents non-tested cutter/rock interactions between a plurality of cutters of different cutter sizes and a plurality of rock types. 
 
 
     
     
       9. The computing system of  claim 8 , wherein the operations further comprise:
 determining cutter force estimates using the second neural network model, wherein the cutter force estimates are determined for the non-tested cutter/rock interactions; and 
 executing a computer-based instruction based on the second neural network model or the cutter force estimates, wherein the computer-based instruction includes at least one selected from the group consisting of:
 executing a computer-based simulation based on the cutter force estimates; 
 adjusting a drilling plan based on results of the computer-based simulation; 
 adjusting a maintenance plan based the results of the computer-based simulation; 
 adjusting operations of a cutter based on the results of the computer-based simulation; 
 modifying a workflow based on the results of the computer-based simulation; 
 providing the calibrated analytical model or data derived from the calibrated analytical model to a simulation system; 
 providing the first neural network model or data derived from the first neural network model to a simulation system; 
 providing the second neural network model or data derived from the second neural network model to a simulation system; 
 setting up automatic synthetic rock file generation workflow; and 
 
 visually presenting the second neural network model or visually present cutter/rock interaction information. 
 
     
     
       10. The computing system of  claim 8 , wherein the operations further comprise refining the first neural network model or the second neural network model based on experimental data. 
     
     
       11. The computing system of  claim 8 , wherein the calibrated analytical model is calibrated using model-based inversion. 
     
     
       12. The computing system of  claim 8 , wherein the calibrated analytical model is a 3D model. 
     
     
       13. The computing system of  claim 8 , wherein the training the first neural network and the training the second neural network are based on machine learning techniques. 
     
     
       14. The computing system of  claim 8 , wherein:
 the first neural network is used to obtain cutter rock forces based on:
 cutter size, 
 confinement pressure, 
 back rake angle, 
 side rake angle, and 
 depth; and 
 
 the second neural network model is used to obtain cutter rock forces based on:
 rock type, 
 cutter size, 
 confinement pressure, 
 back rake angle, 
 side rake angle, and 
 
 depth. 
 
     
     
       15. A non-transitory computer-readable medium storing instructions that, when executed by one or more processors of a computing system, cause the computing system to perform operations, the operations comprising:
 receiving test data representing a cutter/rock interaction for a cutter/rock pair; 
 calibrating an analytical model to represent the cutter/rock interaction for the cutter/rock pair; 
 applying the calibrated analytical model to expand the test data to form one of a plurality of expanded test datasets; 
 generating a first neural network model, of a plurality of first neural network models, representing cutter/rock interactions between a plurality of cutters of different cutter sizes and a particular rock type, wherein the first neural network is generated using the plurality of expanded test datasets as training input; and 
 generating a second neural network model using the plurality of first neural network models as training input, wherein the second neural network model represents non-tested cutter/rock interactions between a plurality of cutters of different cutter sizes and a plurality of rock types. 
 
     
     
       16. The computer-readable medium of  claim 15 , wherein the operations further comprise:
 determining cutter force estimates using the second neural network model, wherein the cutter force estimates are determined for the non-tested cutter/rock interactions; and 
 executing a computer-based instruction based on the second neural network model or the cutter force estimates, wherein the computer-based instruction includes at least one selected from the group consisting of:
 executing a computer-based simulation based on the cutter force estimates; 
 adjusting a drilling plan based on results of the computer-based simulation; 
 adjusting a maintenance plan based the results of the computer-based simulation; 
 adjusting operations of a cutter based on the results of the computer-based simulation; 
 modifying a workflow based on the results of the computer-based simulation; 
 providing the calibrated analytical model or data derived from the calibrated analytical model to a simulation system; 
 providing the first neural network model or data derived from the first neural network model to a simulation system; 
 providing the second neural network model or data derived from the second neural network model to a simulation system; 
 setting up automatic synthetic rock file generation workflow; and 
 
 visually presenting the second neural network model or visually present cutter/rock interaction information. 
 
     
     
       17. The computer-readable medium of  claim 15 , wherein the operations further comprise refining the first neural network model or the second neural network model based on experimental data. 
     
     
       18. The computer-readable medium of  claim 15 , wherein the calibrated analytical model is calibrated using model-based inversion. 
     
     
       19. The computer-readable medium of  claim 15 , wherein the training the first neural network and the training the second neural network are based on machine learning techniques. 
     
     
       20. The computer-readable medium of  claim 15 , wherein:
 the first neural network is used to obtain cutter rock forces based on:
 cutter size, 
 confinement pressure, 
 back rake angle, 
 side rake angle, and 
 depth; and 
 
 the second neural network model is used to obtain cutter rock forces based on:
 rock type, 
 cutter size, 
 confinement pressure, 
 back rake angle, 
 side rake angle, and 
 
 depth.